UVa AIML Seminar
The AI and Machine Learning Seminar @ UVa

Student Flash Talks & Simulating Disease Progression via Progressive Image Editing

Students & Kaizhao Liang
UVA & SambaNova Systems

Time: 2023-11-29, 12:00 - 13:00 ET
Location: Rice 540 and Zoom

Student Flash Talks

Tyler Spears: Predicting Spatially-Continuous White Matter Fiber Orientation Functions

Shen Zhu: Quantifying Hippocampal Shape Asymmetry in Alzheimer’s Disease using Optimal Shape Correspondences

Contributed Talk

Kaizhao Liang

Title: Simulating Disease Progression via Progressive Image Editing

Abstract: Disease progression trajectories can greatly affect the quality and efficacy of clinical diagnosis, prognosis, and treatment. However, one major challenge is the lack of longitudinal medical imaging monitoring of individual patients over time. To address this issue, we propose Progressive Image Editing (PIE) method that enables controlled manipulation of disease-related image features, facilitating precise and realistic disease progression simulation in imaging space. Specifically, we leverage recent advancements in text-to-image generative models to simulate disease progression accurately and personalize it for each patient. We also theoretically analyze the iterative refining process in our framework as a gradient descent with an exponentially decayed learning rate. To validate our framework, we conduct experiments in three medical imaging domains. Our results demonstrate the superiority of PIE over existing methods such as Stable Diffusion Video and Style-Based Manifold Extrapolation based on CLIP score (Realism) and Disease Classification Confidence (Alignment). Our user study collected feedback from 35 veteran physicians to assess the generated progressions. Remarkably, 76.2% of the feedback agrees with the fidelity of the generated progressions. PIE can allow healthcare providers to model disease imaging trajectories over time, predict future treatment responses, fill in missing imaging data in clinical records, and improve medical education.

Bio: Kaizhao Liang, as a Principal Machine Learning Engineer at SambaNova Systems, brings a substantial amount of experience and expertise to his role. His background is rich with insights from both academic research and practical industry experience. In academia, His focus has been on cutting-edge fields such as adversarial machine learning and generative AI. In the industry setting, his responsibilities have sharpened his skills in AI accelerators and the deployment of deep learning models in production environments. He has been instrumental in designing and implementing software frameworks that are specifically tailored for the training of large-scale neural networks. Moreover, he has been innovating efficient algorithms designed for specialized hardware. His work particularly emphasizes dataflow and structured sparsity techniques, which are crucial for optimizing inference speed. Kaizhao Liang’s leadership extends beyond technical expertise; he has successfully led a diverse, cross-functional team. This team includes compiler experts, data collection specialists, and researchers who contribute to publications.